Selection of features and hidden Markov model parameters for English word recognition from Leap Motion air-writing trajectories

Abstract

Air-writing recognition is relevant in areas such as natural human-computer interaction, augmented reality, and virtual reality. A trajectory is the most natural way to represent air writing. We analyze the recognition accuracy of words written in air considering five features, namely, writing direction, cur-vature, trajectory, orthocenter, and ellipsoid, as well as different parameters of a hidden Markov model classifier. Experiments were performed on two representative datasets, whose sample trajectories were collected using a Leap Motion Controller from a fingertip performing air writing. Dataset D1 contains 840 English words from 21 classes, and dataset D2 contains 1600 English words from 40 classes. A genetic algorithm was combined with a hid-den Markov model classifier to obtain the best subset of features. Combination {trajectory, orthocenter, writing direction, curvature} provided the best feature set, achieving recognition accuracies on datasets D1 and D2 of 98.81% and 83.58%, respectively.

Keywords

• air writing
• classification
• feature selection
• leap motion controller
• word recognition